# Semi-Supervised Few-Shot Classification on tieredImagenet (test)

Source: [Semi-Supervised Few-Shot Classification on tieredImagenet (test)](<https://www.sota2.com/research/sota/semi-supervised-few-shot-classification-on-tieredimagenet-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:21:02.190Z

Evaluation of semi-supervised few-shot image classification performance on the test split of the tieredImagenet dataset, focusing on 1-shot and 5-shot accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Semi-Supervised Few-Shot Classification |
| Dataset (including any stated split) | tieredImagenet (test) |
| Metric | 1-Shot Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [1-Shot Accuracy](<https://www.sota2.com/research/sota/semi-supervised-few-shot-classification-on-tieredimagenet-test.md?metric=1-Shot%20Accuracy>): Higher is better; unit: PERCENT.

- [5-Shot Accuracy](<https://www.sota2.com/research/sota/semi-supervised-few-shot-classification-on-tieredimagenet-test.md?metric=5-Shot%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | 1-Shot Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| EPNetSSL | 83.69 | Not recorded | 68fa67e61e209131cea18f9a |
| --NetSSL | 82.03 | Not recorded | 68fa67e61e209131cea18f9a |
| EPNetSSL | 81.79 | Not recorded | 68fa67e61e209131cea18f9a |
| --NetSSL | 80.26 | Not recorded | 68fa67e61e209131cea18f9a |
| EPNet | 78.5 | Not recorded | 68fa67e61e209131cea18f9a |
| LST | 77.7 | Not recorded | 68fa67e61e209131cea18f9a |
| EPNet | 76.53 | Not recorded | 68fa67e61e209131cea18f9a |
| EPNetSSL | 66.63 | Not recorded | 68fa67e61e209131cea18f9a |
| --NetSSL | 65.01 | Not recorded | 68fa67e61e209131cea18f9a |
| EPNet | 59.97 | Not recorded | 68fa67e61e209131cea18f9a |
| TPNSSL | 55.74 | Not recorded | 68fa67e61e209131cea18f9a |

### EPNetSSL

1-Shot Accuracy: 83.69. Result ID: 698d4a988b517eb43320656b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### --NetSSL

1-Shot Accuracy: 82.03. Result ID: 698d4a988b517eb43320656a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### EPNetSSL

1-Shot Accuracy: 81.79. Result ID: 698d4a988b517eb433206568.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"RESNET-12","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### --NetSSL

1-Shot Accuracy: 80.26. Result ID: 698d4a988b517eb433206567.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"RESNET-12","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### EPNet

1-Shot Accuracy: 78.5. Result ID: 698d4a988b517eb433206569.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### LST

1-Shot Accuracy: 77.7. Result ID: 698d4a988b517eb433206565.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa667a1e209131cea10722.md>)

[Implementation](<https://www.sota2.com/github.com/xinzheli1217/learning-to-self-train>)

Recorded evaluation configuration: {"Backbone":"RESNET-12","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### EPNet

1-Shot Accuracy: 76.53. Result ID: 698d4a988b517eb433206566.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"RESNET-12","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### EPNetSSL

1-Shot Accuracy: 66.63. Result ID: 698d4a988b517eb433206564.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"CONV-4","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### --NetSSL

1-Shot Accuracy: 65.01. Result ID: 698d4a988b517eb433206563.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"CONV-4","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### EPNet

1-Shot Accuracy: 59.97. Result ID: 698d4a988b517eb433206562.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Implementation](<https://github.com/ElementAI/embedding-propagation>)

Recorded evaluation configuration: {"Backbone":"CONV-4","Number of unlabeled samples":100}. This record does not assert independent reproduction.

### TPNSSL

1-Shot Accuracy: 55.74. Result ID: 698d4a988b517eb433206561.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67e61e209131cea18f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65581e209131cea09e59.md>)

Recorded evaluation configuration: {"Backbone":"CONV-4","Number of unlabeled samples":100}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.